Uncertainty Minimization for Personalized Federated Semi-Supervised Learning

by   Yanhang Shi, et al.

Since federated learning (FL) has been introduced as a decentralized learning technique with privacy preservation, statistical heterogeneity of distributed data stays the main obstacle to achieve robust performance and stable convergence in FL applications. Model personalization methods have been studied to overcome this problem. However, existing approaches are mainly under the prerequisite of fully labeled data, which is unrealistic in practice due to the requirement of expertise. The primary issue caused by partial-labeled condition is that, clients with deficient labeled data can suffer from unfair performance gain because they lack adequate insights of local distribution to customize the global model. To tackle this problem, 1) we propose a novel personalized semi-supervised learning paradigm which allows partial-labeled or unlabeled clients to seek labeling assistance from data-related clients (helper agents), thus to enhance their perception of local data; 2) based on this paradigm, we design an uncertainty-based data-relation metric to ensure that selected helpers can provide trustworthy pseudo labels instead of misleading the local training; 3) to mitigate the network overload introduced by helper searching, we further develop a helper selection protocol to achieve efficient communication with negligible performance sacrifice. Experiments show that our proposed method can obtain superior performance and more stable convergence than other related works with partial labeled data, especially in highly heterogeneous setting.


page 1

page 2

page 3

page 4

page 5

page 7

page 8

page 9


Efficient Semi-Supervised Federated Learning for Heterogeneous Participants

Federated Learning (FL) has emerged to allow multiple clients to collabo...

Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels

Many existing FL methods assume clients with fully-labeled data, while i...

Federated Semi-Supervised Learning with Prototypical Networks

With the increasing computing power of edge devices, Federated Learning ...

Federated Semi-Supervised Learning with Class Distribution Mismatch

Many existing federated learning (FL) algorithms are designed for superv...

FedProp: Cross-client Label Propagation for Federated Semi-supervised Learning

Federated learning (FL) allows multiple clients to jointly train a machi...

RSCFed: Random Sampling Consensus Federated Semi-supervised Learning

Federated semi-supervised learning (FSSL) aims to derive a global model ...

Collaboratively Learning Linear Models with Structured Missing Data

We study the problem of collaboratively learning least squares estimates...

Please sign up or login with your details

Forgot password? Click here to reset